Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Multidimensional opinion mining from social data

Cortis, Keith orcid logoORCID: 0000-0002-9748-0340 (2022) Multidimensional opinion mining from social data. PhD thesis, Dublin City University.

Abstract
Social media popularity and importance is on the increase due to people using it for various types of social interaction across multiple channels. This thesis focuses on the evolving research area of Social Opinion Mining, tasked with the identification of multiple opinion dimensions, such as subjectivity, sentiment polarity, emotion, affect, sarcasm, and irony, from user-generated content represented across multiple social media platforms and in various media formats, like textual, visual, and audio. Mining people’s social opinions from social sources, such as social media platforms and newswires commenting sections, is a valuable business asset that can be utilised in many ways and in multiple domains, such as Politics, Finance, and Government. The main objective of this research is to investigate how a multidimensional approach to Social Opinion Mining affects fine-grained opinion search and summarisation at an aspect-based level and whether such a multidimensional approach outperforms single dimension approaches in the context of an extrinsic human evaluation conducted in a real-world context: the Malta Government Budget, where five social opinion dimensions are taken into consideration, namely subjectivity, sentiment polarity, emotion, irony, and sarcasm. This human evaluation determines whether the multidimensional opinion summarisation results provide added-value to potential end-users, such as policy-makers and decision-takers, thereby providing a nuanced voice to the general public on their social opinions on topics of a national importance. Results obtained indicate that a more fine-grained aspect-based opinion summary based on the combined dimensions of subjectivity, sentiment polarity, emotion, and sarcasm or irony is more informative and more useful than one based on sentiment polarity only. This research contributes towards the advancement of intelligent search and information retrieval from social data and impacts entities utilising Social Opinion Mining results towards effective policy formulation, policy-making, decision-making, and decision-taking at a strategic level.
Metadata
Item Type:Thesis (PhD)
Date of Award:29 August 2022
Refereed:No
Supervisor(s):Davis, Brian
Uncontrolled Keywords:Opinion Mining, Opinion Summarisation, Multidimensional Opinion Mining
Subjects:Computer Science > Artificial intelligence
Computer Science > Computational linguistics
Computer Science > Information retrieval
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Funders:Science Foundation Ireland (SFI) grant number 13/RC/2106 P1/P2
ID Code:27661
Deposited On:10 Nov 2022 14:01 by Brian Davis . Last Modified 10 Nov 2022 14:01
Documents

Full text available as:

[thumbnail of PhD-thesis-Keith-Cortis-DCU-29-08-22.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0
4MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record